An Improved Rolling Bearing Fault Diagnosis Method based on Enhanced Feature Extraction and Regularized SVM

Ningjiang Han; Chenxin Gong

doi:10.6919/ICJE.202606_12(6).0001

An Improved Rolling Bearing Fault Diagnosis Method based on Enhanced Feature Extraction and Regularized SVM

Ningjiang Han, Chenxin Gong

International Core Journal of Engineering, (2026), Vol.12, No.6, pp.1-10

Published: June 18, 2026

DOI: 10.6919/ICJE.202606_12(6).0001

PDF: Download Full Text PDF

Abstract

Rolling bearing fault diagnosis is critical for ensuring the safety and reliability of rotating machinery. This paper proposes an improved fault diagnosis method that addresses the overfitting problem commonly observed in traditional approaches. The method employs a 9-dimensional enhanced feature vector combining time-domain statistical features (RMS, kurtosis, crest factor, skewness) with envelope spectrum features (BPFO, BPFI, BSF amplitudes, band energy ratio, spectral entropy). A data augmentation strategy using Gaussian noise perturbation is introduced to increase training sample diversity. The RBF-SVM classifier is regularized with optimized parameters (C=1, γ=0.1) to prevent overfitting. Validated on the CWRU bearing dataset with multiple damage severities, the proposed method achieves 98.5% accuracy under strict temporal-split validation with a train-test gap of only 1.5%, compared to 87.0% for the baseline model. The results demonstrate that enhanced features combined with proper regularization effectively resolve overfitting while maintaining high diagnostic performance.

Keywords: Rolling Bearing; Fault Diagnosis; Feature Extraction; Support Vector Machine; Regularization; Overfitting; CWRU Dataset.

APA Citation: Ningjiang Han, Chenxin Gong (2026). An Improved Rolling Bearing Fault Diagnosis Method based on Enhanced Feature Extraction and Regularized SVM. International Core Journal of Engineering, 12(6), 1-10. https://doi.org/10.6919/ICJE.202606_12(6).0001

References

Smith, W. A., & Randall, R. B. (2015). The diagnostic of rolling element bearings by use of the Case Western Reserve University data: A benchmark study. Mechanical Systems and Signal Processing, 64–65, 100–131.
Antoni, J. (2006). The spectral kurtosis, as a method of describing non-stationary signals. Mechanical Systems and Signal Processing, 20(2), 282–307.
Widodo, A., & Yang, B. S. (2007). The application of support vector machine to machine condition monitoring and fault diagnosis. Mechanical Systems and Signal Processing, 21(6), 2560–2574.
Lei, Y., et al. (2020). Machine fault diagnosis based on applications of machine learning: A review and roadmap. Mechanical Systems and Signal Processing, 138, 106587.
Zhang, H. J., Zhao, H. J., & Liu, S. L. (2018). Bearing fault diagnosis based on Hilbert envelope spectrum and SVM. Vibration and Shock, 37(10), 205–211.
Case Western Reserve University. (n.d.). Bearing vibration data sets [Data set]. https://engineering.case.edu/bearingdatacenter
Chu, F. L., Peng, Z. K., & Feng, Z. P. (2013). The modern methods of signal processing in mechanical fault diagnosis. Science Press.